brand-guidelines

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and apply styles to external artifacts, which creates a vector where instructions embedded in those artifacts could attempt to influence the agent's behavior during the styling process.
  • Ingestion points: Any artifact or document provided to the agent for brand styling as described in SKILL.md.
  • Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore instructions embedded within the content it is styling.
  • Capability inventory: The technical details mention the use of 'python-pptx' for precise brand matching, which implies that the agent using this skill is expected to have capabilities for reading and writing presentation files.
  • Sanitization: There are no instructions or logic provided to sanitize, filter, or validate the content of the artifacts being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 04:39 AM